mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-27 07:15:15 +08:00
9e5552aa13
Signed-off-by: kaln27 <liaojuncheng123@foxmail.com> Co-authored-by: mgoin <mgoin64@gmail.com>
25 lines
980 B
Plaintext
25 lines
980 B
Plaintext
#include "scaled_mm_kernels.hpp"
|
|
#include "scaled_mm_sm120_fp8_dispatch.cuh"
|
|
#include "cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp"
|
|
|
|
namespace vllm {
|
|
|
|
void cutlass_scaled_mm_sm120_fp8(torch::Tensor& out, torch::Tensor const& a,
|
|
torch::Tensor const& b,
|
|
torch::Tensor const& a_scales,
|
|
torch::Tensor const& b_scales,
|
|
std::optional<torch::Tensor> const& bias) {
|
|
TORCH_CHECK(a_scales.is_contiguous() && b_scales.is_contiguous());
|
|
if (bias) {
|
|
TORCH_CHECK(bias->dtype() == out.dtype(),
|
|
"currently bias dtype must match output dtype ", out.dtype());
|
|
return cutlass_scaled_mm_sm120_fp8_epilogue<c3x::ScaledEpilogueBias>(
|
|
out, a, b, a_scales, b_scales, *bias);
|
|
} else {
|
|
return cutlass_scaled_mm_sm120_fp8_epilogue<c3x::ScaledEpilogue>(
|
|
out, a, b, a_scales, b_scales);
|
|
}
|
|
}
|
|
|
|
} // namespace vllm
|